annahdo / implementing_activation_steeringLinks
A collection of different ways to implement accessing and modifying internal model activations for LLMs
☆19Updated 11 months ago
Alternatives and similar repositories for implementing_activation_steering
Users that are interested in implementing_activation_steering are comparing it to the libraries listed below
Sorting:
- Sparse Autoencoder Training Library☆54Updated 5 months ago
- Open source replication of Anthropic's Crosscoders for Model Diffing☆59Updated 11 months ago
- Experiments with representation engineering☆13Updated last year
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆215Updated this week
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆221Updated 9 months ago
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆97Updated 2 years ago
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Steering vectors for transformer language models in Pytorch / Huggingface☆125Updated 7 months ago
- ☆127Updated last year
- ☆34Updated last year
- ☆242Updated last year
- Steering Llama 2 with Contrastive Activation Addition☆187Updated last year
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆72Updated last year
- Attribution-based Parameter Decomposition☆30Updated 3 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆209Updated 2 weeks ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆92Updated last year
- ☆29Updated last year
- Algebraic value editing in pretrained language models☆66Updated last year
- ☆23Updated last year
- Erasing concepts from neural representations with provable guarantees☆236Updated 8 months ago
- A library for efficient patching and automatic circuit discovery.☆77Updated 2 months ago
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆24Updated 10 months ago
- ☆187Updated 2 months ago
- Stanford NLP Python library for benchmarking the utility of LLM interpretability methods☆134Updated 3 months ago
- Code for reproducing our paper "Not All Language Model Features Are Linear"☆80Updated 10 months ago
- Mechanistic Interpretability Visualizations using React☆291Updated 9 months ago
- PyTorch and NNsight implementation of AtP* (Kramar et al 2024, DeepMind)☆19Updated 8 months ago
- ☆276Updated last year
- Measuring the situational awareness of language models☆38Updated last year
- ☆124Updated last year